A per-unit curve rotated decoupling method for CNN-TCN based day-ahead load forecasting

Shengtao He, Canbing Li, Xubin Liu*, Xinyu Chen, Mohammad Shahidehpour, Tao Chen, Bin Zhou, Qiuwei Wu

*Corresponding author for this work

    Research output: Contribution to journalJournal articleResearchpeer-review

    130 Downloads (Pure)

    Abstract

    The existing load forecasting method based on the per-unit curve static decoupling (PCSD) would easily lead to the deviation and translation of forecasting results. To tackle this challenge, a per-unit curve rotated decoupling (PCRD) method is proposed for day-ahead load forecasting with convolutional neural network and temporal convolutional network framework. The PCRD method decomposes the load into three parts: the rotated per-unit load curve, the 0 AM load, and the daily average load. The shape feature of the load curve is extracted by CNN, the temporal features of the 0 AM load and daily average load are extracted by TCN. The rotation operation is to rotate the per-unit load curve at the midpoint of the curve until the first load point is aligned to the same point, in order to improve the similarity of per-unit load curves and to alleviate the deflection of forecasting results. The 0 AM load can verify the accuracy of the daily average load, which alleviates the translation of forecasting results. Several experimental results show that the proposed method has higher accuracy and stability than the existing PCSD method. After repeated experiments on multiple data sets, the generalization ability of the model is also verified.

    Original languageEnglish
    JournalIET Generation Transmission and Distribution
    Volume15
    Issue number19
    Pages (from-to)2773-2786
    ISSN1751-8687
    DOIs
    Publication statusPublished - Oct 2021

    Bibliographical note

    Publisher Copyright:
    © 2021 The Authors. IET Generation, Transmission & Distribution published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology

    Fingerprint

    Dive into the research topics of 'A per-unit curve rotated decoupling method for CNN-TCN based day-ahead load forecasting'. Together they form a unique fingerprint.

    Cite this